Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4590 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.1541. Min Range: -5.1541

Max Act: 4.9980. Min Act: -0.0000

Data Index: 1538682 (Python Code)

Max Activating Token Index: 18

Text #1

Max Range: 5.1541. Min Range: -5.1541

Max Act: 5.1541. Min Act: -0.0000

Data Index: 1615795 (Python Code)

Max Activating Token Index: 27

Text #2

Max Range: 5.1541. Min Range: -5.1541

Max Act: 4.8106. Min Act: -0.0000

Data Index: 1387706 (Python Code)

Max Activating Token Index: 6

Text #3

Max Range: 5.1541. Min Range: -5.1541

Max Act: 4.7885. Min Act: -0.0000

Data Index: 1504220 (Python Code)

Max Activating Token Index: 126

Text #4

Max Range: 5.1541. Min Range: -5.1541

Max Act: 4.9577. Min Act: -0.0000

Data Index: 1418897 (Python Code)

Max Activating Token Index: 54

Text #5

Max Range: 5.1541. Min Range: -5.1541

Max Act: 4.8230. Min Act: -0.0000

Data Index: 1493220 (Python Code)

Max Activating Token Index: 203

Text #6

Max Range: 5.1541. Min Range: -5.1541

Max Act: 4.8232. Min Act: -0.0000

Data Index: 1391451 (Python Code)

Max Activating Token Index: 33

Text #7

Max Range: 5.1541. Min Range: -5.1541

Max Act: 4.6450. Min Act: -0.0000

Data Index: 1372580 (Python Code)

Max Activating Token Index: 16

Text #8

Max Range: 5.1541. Min Range: -5.1541

Max Act: 4.4495. Min Act: -0.0000

Data Index: 1652702 (Python Code)

Max Activating Token Index: 70

Text #9

Max Range: 5.1541. Min Range: -5.1541

Max Act: 4.7756. Min Act: -0.0000

Data Index: 1506880 (Python Code)

Max Activating Token Index: 855

Text #10

Max Range: 5.1541. Min Range: -5.1541

Max Act: 4.6551. Min Act: -0.0000

Data Index: 1543661 (Python Code)

Max Activating Token Index: 235

Text #11

Max Range: 5.1541. Min Range: -5.1541

Max Act: 4.4416. Min Act: -0.0000

Data Index: 1648633 (Python Code)

Max Activating Token Index: 35

Text #12

Max Range: 5.1541. Min Range: -5.1541

Max Act: 4.2536. Min Act: -0.0000

Data Index: 1374652 (Python Code)

Max Activating Token Index: 82

Text #13

Max Range: 5.1541. Min Range: -5.1541

Max Act: 4.3819. Min Act: -0.0000

Data Index: 1584100 (Python Code)

Max Activating Token Index: 309

Text #14

Max Range: 5.1541. Min Range: -5.1541

Max Act: 4.3688. Min Act: -0.0000

Data Index: 1628376 (Python Code)

Max Activating Token Index: 61

Text #15

Max Range: 5.1541. Min Range: -5.1541

Max Act: 4.0556. Min Act: -0.0000

Data Index: 1451593 (Python Code)

Max Activating Token Index: 134

Text #16

Max Range: 5.1541. Min Range: -5.1541

Max Act: 4.2459. Min Act: -0.0000

Data Index: 1633206 (Python Code)

Max Activating Token Index: 637

Text #17

Max Range: 5.1541. Min Range: -5.1541

Max Act: 3.2157. Min Act: -0.0000

Data Index: 1478293 (Python Code)

Max Activating Token Index: 242

Text #18

Max Range: 5.1541. Min Range: -5.1541

Max Act: 3.9657. Min Act: -0.0000

Data Index: 1592556 (Python Code)

Max Activating Token Index: 159

Text #19

Max Range: 5.1541. Min Range: -5.1541

Max Act: 3.9914. Min Act: -0.0000

Data Index: 1653230 (Python Code)

Max Activating Token Index: 70